Prometheus MCP Server

io.github.pab1it0由 GitHub 帳號 pab1it0 發布v1.6.2更新於 Oct 24, 2026

MCP server providing Prometheus metrics access and PromQL query execution for AI assistants

發布方自己的服務：Prometheus MCP

已驗證STDIO僅桌面安全與監控資料與分析

概覽

AI 產生的概覽

把 AI 助理連接到 Prometheus 伺服器，讓它能執行 PromQL 即時與範圍查詢，並瀏覽指標與抓取目標。

可以做什麼
  • 對 Prometheus 執行 PromQL 即時查詢，以及帶起訖時間與步長的範圍查詢
  • 列出可用指標、取得單一或批次指標中繼資料，並可依名稱或描述搜尋
  • 檢視抓取目標，支援依狀態與抓取池篩選及分頁
  • 檢查服務健康狀態，並可將查詢結果在 Prometheus 介面中開啟
適用情境
適合想讓助理直接在 Prometheus 中追查指標、儀表板或故障，或在撰寫查詢前先了解有哪些指標的情況，省去手動複製 PromQL 結果。
執行需求
以本機程序執行，通常透過 Docker 執行已發布的容器映像（另提供 Kubernetes 的 Helm chart）。需要可連線的 Prometheus 位址（PROMETHEUS_URL）；可選用基本驗證 PROMETHEUS_USERNAME 與 PROMETHEUS_PASSWORD、權杖驗證 PROMETHEUS_TOKEN、雙向 TLS 的 PROMETHEUS_CLIENT_CERT 與 PROMETHEUS_CLIENT_KEY，以及自訂標頭 PROMETHEUS_CUSTOM_HEADERS。
安裝前請注意
需要 Prometheus 執行個體的憑證：PROMETHEUS_PASSWORD、PROMETHEUS_TOKEN 與用戶端私鑰路徑 PROMETHEUS_CLIENT_KEY 屬於機密，應透過環境變數傳入而非寫進版控設定。PROMETHEUS_URL_SSL_VERIFY 可設為 False，會關閉 TLS 憑證檢查。查詢結果與指標中繼資料會傳送給 AI 用戶端，且除非設定 PROMETHEUS_DISABLE_LINKS，結果會包含 Prometheus 介面連結。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Prometheus MCP Server，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

Prometheus MCP Server

[GitHub Container Registry] [Helm Chart] [GitHub Release] [Codecov] [Python] [License]

Give AI assistants the power to query your Prometheus metrics.

A Model Context Protocol (MCP) server that provides access to your Prometheus metrics and queries through standardized MCP interfaces, allowing AI assistants to execute PromQL queries and analyze your metrics data.

Getting Started

Prerequisites

  • Prometheus server accessible from your environment
  • MCP-compatible client (Claude Desktop, VS Code, Cursor, Windsurf, etc.)

Installation Methods

Claude Desktop

Add to your Claude Desktop configuration:

json
{  "mcpServers": {    "prometheus": {      "command": "docker",      "args": [        "run",        "-i",        "--rm",        "-e",        "PROMETHEUS_URL",        "ghcr.io/pab1it0/prometheus-mcp-server:latest"      ],      "env": {        "PROMETHEUS_URL": "<your-prometheus-url>"      }    }  }}
Claude Code

Install via the Claude Code CLI:

bash
claude mcp add prometheus --env PROMETHEUS_URL=http://your-prometheus:9090 -- docker run -i --rm -e PROMETHEUS_URL ghcr.io/pab1it0/prometheus-mcp-server:latest
VS Code / Cursor / Windsurf

Add to your MCP settings in the respective IDE:

json
{  "prometheus": {    "command": "docker",    "args": [      "run",      "-i",      "--rm",      "-e",      "PROMETHEUS_URL",      "ghcr.io/pab1it0/prometheus-mcp-server:latest"    ],    "env": {      "PROMETHEUS_URL": "<your-prometheus-url>"    }  }}
Docker Desktop

The easiest way to run the Prometheus MCP server is through Docker Desktop:

[Add to Docker Desktop]

  1. Via MCP Catalog: Visit the Prometheus MCP Server on Docker Hub and click the button above

  2. Via MCP Toolkit: Use Docker Desktop's MCP Toolkit extension to discover and install the server

  3. Configure your connection using environment variables (see Configuration Options below)

Manual Docker Setup

Run directly with Docker:

bash
# With environment variablesdocker run -i --rm \  -e PROMETHEUS_URL="http://your-prometheus:9090" \  ghcr.io/pab1it0/prometheus-mcp-server:latest
# With authenticationdocker run -i --rm \  -e PROMETHEUS_URL="http://your-prometheus:9090" \  -e PROMETHEUS_USERNAME="admin" \  -e PROMETHEUS_PASSWORD="password" \  ghcr.io/pab1it0/prometheus-mcp-server:latest
Helm Chart (Kubernetes)

Deploy to Kubernetes using the Helm chart from the OCI registry:

bash
helm install prometheus-mcp-server \  oci://ghcr.io/pab1it0/charts/prometheus-mcp-server \  --version 1.1.1 \  --set prometheus.url="http://prometheus:9090"

With authentication:

bash
helm install prometheus-mcp-server \  oci://ghcr.io/pab1it0/charts/prometheus-mcp-server \  --version 1.1.1 \  --set prometheus.url="http://prometheus:9090" \  --set auth.username="admin" \  --set auth.password="secret"

With a custom values file:

bash
helm install prometheus-mcp-server \  oci://ghcr.io/pab1it0/charts/prometheus-mcp-server \  --version 1.1.1 \  -f values.yaml

See the chart values for all available configuration options.

Configuration Options

VariableDescriptionRequired
PROMETHEUS_URLURL of your Prometheus serverYes
PROMETHEUS_URL_SSL_VERIFYSet to False to disable SSL verificationNo
PROMETHEUS_DISABLE_LINKSSet to True to disable Prometheus UI links in query results (saves context tokens)No
PROMETHEUS_REQUEST_TIMEOUTRequest timeout in seconds to prevent hanging requests (DDoS protection)No (default: 30)
PROMETHEUS_USERNAMEUsername for basic authenticationNo
PROMETHEUS_PASSWORDPassword for basic authenticationNo
PROMETHEUS_TOKENBearer token for authenticationNo
PROMETHEUS_CLIENT_CERTPath to client certificate file for mutual TLS authenticationNo
PROMETHEUS_CLIENT_KEYPath to client private key file for mutual TLS authenticationNo
REQUESTS_CA_BUNDLEPath to CA bundle file for verifying the server's TLS certificate (standard requests library env var)No
ORG_IDOrganization ID for multi-tenant setupsNo
PROMETHEUS_MCP_SERVER_TRANSPORTTransport mode (stdio, http, sse)No (default: stdio)
PROMETHEUS_MCP_BIND_HOSTHost for HTTP transportNo (default: 127.0.0.1)
PROMETHEUS_MCP_BIND_PORTPort for HTTP transportNo (default: 8080)
PROMETHEUS_MCP_STATELESS_HTTPEnable stateless HTTP mode for multi-replica supportNo (default: False)
PROMETHEUS_CUSTOM_HEADERSCustom headers as JSON stringNo
TOOL_PREFIXPrefix for all tool names (e.g., staging results in staging_execute_query). Useful for running multiple instances targeting different environments in CursorNo

Available Tools

ToolCategoryDescription
health_checkSystemHealth check endpoint for container monitoring and status verification
execute_queryQueryExecute a PromQL instant query against Prometheus
execute_range_queryQueryExecute a PromQL range query with start time, end time, and step interval
list_metricsDiscoveryList all available metrics in Prometheus with pagination and filtering support
get_metric_metadataDiscoveryGet metadata for one metric or bulk metadata with optional filtering
get_targetsDiscoveryGet scrape targets, with server-side state/scrape_pool filtering and optional pagination

The list of tools is configurable, so you can choose which tools you want to make available to the MCP client. This is useful if you don't use certain functionality or if you don't want to take up too much of the context window.

Features

  • Execute PromQL queries against Prometheus
  • Discover and explore metrics
    • List available metrics
    • Get metadata for specific metrics
    • Search metric metadata by name or description in a single call
    • View instant query results
    • View range query results with different step intervals
    • Open range query results in the Prometheus UI with the same time window and resolution
  • Authentication support
    • Basic auth from environment variables
    • Bearer token auth from environment variables
  • Docker containerization support
  • Provide interactive tools for AI assistants

Development

Contributions are welcome! Please see our Contributing Guide for detailed information on how to get started, coding standards, and the pull request process.

This project uses uv to manage dependencies. Install uv following the instructions for your platform:

bash
curl -LsSf https://astral.sh/uv/install.sh | sh

You can then create a virtual environment and install the dependencies with:

bash
uv venvsource .venv/bin/activate  # On Unix/macOS.venv\Scripts\activate     # On Windowsuv pip install -e .

Testing

The project includes a comprehensive test suite that ensures functionality and helps prevent regressions.

Run the tests with pytest:

bash
# Install development dependenciesuv pip install -e ".[dev]"
# Run the testspytest
# Run with coverage reportpytest --cov=src --cov-report=term-missing

When adding new features, please also add corresponding tests.

License

MIT

來源：README.md，提交 a6bc50b

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包，因此其工具未知。

版本歷史

1
  1. v1.6.2最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

其他 Prometheus 整合

Prometheus MCP

sv.prometheus官方發布者

Prometheus 提供的遠端 MCP 端點，讓 AI 助理在面向代理與創作者的知识網路中搜尋、評分和評論程式設計指南。

Streamable HTTP可網頁執行
知識與記憶尚未收錄Oct 24, 2026

Prometheus MCP Server

由 GitHub 帳號 prometheus 發布

一個API完整的MCP伺服器，用於管理相容Prometheus的後端。AI 翻譯

STDIO僅桌面
安全與監控尚未驗證Nov 3, 2026

Prometheus MCP Server

由 GitHub 帳號 tjhop 發布

讓助理查詢與檢視 Prometheus 相容後端的 MCP 伺服器：PromQL 查詢、標籤、序列、規則、告警、目標與文件。

STDIO僅桌面
雲端與基礎設施尚未驗證Oct 27, 2026

Prometheus Mcp

由 GitHub 帳號 mshegolev 發布

唯讀 MCP 伺服器，讓助理以 PromQL 查詢 Prometheus 指標、列出指標名稱、檢視作用中告警與抓取目標。

STDIO僅桌面
安全與監控尚未驗證Oct 24, 2026

Mcp Prometheus

由 GitHub 帳號 jeanlopezxyz 發布

一個本機 MCP 伺服器，將助理連接到 Prometheus，使其能執行 PromQL 查詢並診斷 Kubernetes/OpenShift 叢集健康狀態。

STDIO僅桌面
雲端與基礎設施尚未驗證Oct 24, 2026